<a  # begin anchor tag
\s  # followed by a space
\w* # followed by any number of alpha-numeric characters
    # this fails to match ["'=/:%?&] and probably many other potential permissable chars in this context and so your regex fails here.
>   # end anchor tag
\w* # any text as long as it's all one word see above point you should be matching any char which is not the beginning of a tag
<   # beginning of a new tag including an end of anchor